csv-detective 0.8.1.dev1362__py3-none-any.whl → 0.8.1.dev1416__py3-none-any.whl

csv_detective/detect_labels/temp/year/__init__.py

@@ -1,44 +1,19 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'year',
-        'annee',
-        'annee depot',
-        'an nais',
-        'exercice',
-        'data year',
-        'annee de publication',
-        'exercice comptable',
-        'annee de naissance',
-        'annee ouverture'
+        "year",
+        "annee",
+        "annee depot",
+        "an nais",
+        "exercice",
+        "data year",
+        "annee de publication",
+        "exercice comptable",
+        "annee de naissance",
+        "annee ouverture",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/parsing/text.py

@@ -8,6 +8,17 @@ def camel_case_split(identifier: str):
     return " ".join([m.group(0) for m in matches])
 
 
+translate_dict = {
+    " ": ["-", "_", "'", ",", "  "],
+    "a": ["à", "â"],
+    "c": ["ç"],
+    "e": ["é", "è", "ê", "é"],
+    "i": ["î", "ï"],
+    "o": ["ô", "ö"],
+    "u": ["ù", "û", "ü"],
+}
+
+
 # Process text
 def _process_text(val: str):
     """Traitement des chaînes de caractères pour les standardiser.
@@ -15,25 +26,36 @@ def _process_text(val: str):
     des méthodes hybrides, mais aucune ne s'est avérée plus performante."""
     val = camel_case_split(val)
     val = val.lower()
-    val = val.replace("-", " ")
-    val = val.replace("_", " ")
-    val = val.replace("'", " ")
-    val = val.replace(",", " ")
-    val = val.replace("  ", " ")
-    val = val.replace("à", "a")
-    val = val.replace("â", "a")
-    val = val.replace("ç", "c")
-    val = val.replace("é", "e")
-    val = val.replace("é", "e")
-    val = val.replace("è", "e")
-    val = val.replace("ê", "e")
-    val = val.replace("î", "i")
-    val = val.replace("ï", "i")
-    val = val.replace("ô", "o")
-    val = val.replace("ö", "o")
-    val = val.replace("î", "i")
-    val = val.replace("û", "u")
-    val = val.replace("ù", "u")
-    val = val.replace("ü", "u")
+    for target in translate_dict:
+        for source in translate_dict[target]:
+            val = val.replace(source, target)
     val = val.strip()
     return val
+
+
+def is_word_in_string(word: str, string: str):
+    # if the substring is too short, the test can become irrelevant
+    return len(word) > 2 and word in string
+
+
+def header_score(header: str, words_combinations_list: list[str]) -> float:
+    """Returns:
+    - 1 if the header is exactly in the specified list
+    - 0.5 if any of the words is within the header
+    - 0 otherwise"""
+    processed_header = _process_text(header)
+
+    header_matches_words_combination = float(
+        any(
+            words_combination == processed_header for words_combination in words_combinations_list
+        )
+    )
+    words_combination_in_header = 0.5 * (
+        any(
+            is_word_in_string(
+                words_combination, processed_header
+            ) for words_combination in words_combinations_list
+        )
+    )
+
+    return max(header_matches_words_combination, words_combination_in_header)

csv_detective/utils.py

@@ -25,6 +25,7 @@ def display_logs_depending_process_time(prompt: str, duration: float):
 
 def is_url(file_path: str) -> bool:
     # could be more sophisticated if needed
+    # using the URL detection test was considered but too broad (schema required to use requests)
     return file_path.startswith('http')
 
 
@@ -32,7 +33,3 @@ def prevent_nan(value: float) -> Optional[float]:
     if math.isnan(value):
         return None
     return value
-
-
-def is_word_in_string(word: str, string: str):
-    return word in string

{csv_detective-0.8.1.dev1362.data → csv_detective-0.8.1.dev1416.data}/data/share/csv_detective/CHANGELOG.md

@@ -2,7 +2,8 @@
 
 ## Current (in progress)
 
-- Nothing yet
+- Refactor label testing [#119](https://github.com/datagouv/csv-detective/pull/119)
+- Better URL detection [#120](https://github.com/datagouv/csv-detective/pull/120)
 
 ## 0.8.0 (2025-05-20)
 

{csv_detective-0.8.1.dev1362.dist-info → csv_detective-0.8.1.dev1416.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csv_detective
-Version: 0.8.1.dev1362
+Version: 0.8.1.dev1416
 Summary: Detect CSV column content
 Home-page: https://github.com/etalab/csv_detective
 Author: Etalab

{csv_detective-0.8.1.dev1362.dist-info → csv_detective-0.8.1.dev1416.dist-info}/RECORD

@@ -3,7 +3,7 @@ csv_detective/cli.py,sha256=itooHtpyfC6DUsL_DchPKe1xo7m0MYJIp1L4R8eqoTk,1401
 csv_detective/explore_csv.py,sha256=IT1-9TbS78p6oeDpQ5T6DQ93xQbobcscyBQb6nh86H4,9082
 csv_detective/load_tests.py,sha256=GILvfkd4OVI-72mA4nzbPlZqgcXZ4wznOhGfZ1ucWkM,2385
 csv_detective/s3_utils.py,sha256=1cIVdQUYY2ovErbMwp72Gqtqx2bkB8nfVhn-QaOFTT0,1451
-csv_detective/utils.py,sha256=8cBKgWifWF7BG_uMfLmxtV45p6PZ4b50NjWXKoAAZ4s,1002
+csv_detective/utils.py,sha256=-tIs9yV7RJPGj65lQ7LjRGch6Iws9UeuIPQsd2uUUJM,1025
 csv_detective/validate.py,sha256=4e7f8bNXPU9GqNx4QXXiaoINyotozbL52JB6psVAjyY,2631
 csv_detective/detect_fields/__init__.py,sha256=7Tz0Niaz0BboA3YVsp_6WPA6ywciwDN4-lOy_Ie_0Y8,976
 csv_detective/detect_fields/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -63,7 +63,7 @@ csv_detective/detect_fields/other/money/__init__.py,sha256=g_ZwBZXl9LhldwFYQotC5
 csv_detective/detect_fields/other/mongo_object_id/__init__.py,sha256=7fcrHsOZAqXp2_N0IjPskYJ_qi4xRlo9iyNNDQVLzsU,156
 csv_detective/detect_fields/other/percent/__init__.py,sha256=vgpekNOPBRuunoVBXMi81rwHv4uSOhe78pbVtQ5SBO8,177
 csv_detective/detect_fields/other/twitter/__init__.py,sha256=qbwLKsTBRFQ4PyTNVeEZ5Hkf5Wwi3ZKclLER_V0YO3g,154
-csv_detective/detect_fields/other/url/__init__.py,sha256=9WaTqCglEsw_lJG_xZsBMdxJXg2yuQ92_fkX6CXWNV0,286
+csv_detective/detect_fields/other/url/__init__.py,sha256=L7h9fZldh1w86XwCx0x3Q1TXSJ_nIId1C-l1yFzZYrA,299
 csv_detective/detect_fields/other/uuid/__init__.py,sha256=3-z0fDax29SJc57zPjNGR6DPICJu6gfuNGC5L3jh4d0,223
 csv_detective/detect_fields/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detect_fields/temp/date/__init__.py,sha256=1a_Ra9fmT4wgGMrcknXP7eN7A2QiaMF0Yjy0-BMihtA,987
@@ -74,60 +74,59 @@ csv_detective/detect_fields/temp/year/__init__.py,sha256=RjsiIHoplnI4Odi5587TzRh
 csv_detective/detect_labels/__init__.py,sha256=BJjWlwTnnDe9nomABDUreu9EMu6IFG3T47d7YCJZbRc,878
 csv_detective/detect_labels/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detect_labels/FR/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/geo/adresse/__init__.py,sha256=ISgpkhy6KwOmKqCt6w_RpxZ7zm5gx2D3mp2UE9D6Pjw,1033
-csv_detective/detect_labels/FR/geo/code_commune_insee/__init__.py,sha256=_QKJX7Og8cL1AYBLjIbvULsy-XJ017G0ZXk7H_GOqdI,1067
-csv_detective/detect_labels/FR/geo/code_departement/__init__.py,sha256=_lU5bXG8hODduVxVyXegZjRR_mxWM3SXfwb6stJbOrU,995
-csv_detective/detect_labels/FR/geo/code_fantoir/__init__.py,sha256=qIFLhkj3vr0lfBHtDwYNhGqLgdzN0w7LRFJByt0pEts,919
-csv_detective/detect_labels/FR/geo/code_postal/__init__.py,sha256=TUquZFf6cuTIvjvox8ReIiOqzJnepCZcLX21KNtWwyo,1040
-csv_detective/detect_labels/FR/geo/code_region/__init__.py,sha256=6I9DpXNMBYJ1bTqAiheFhnMo2vbrz51PdZttrbinGVA,982
-csv_detective/detect_labels/FR/geo/commune/__init__.py,sha256=WQl7z3h0428A-4H5ytry0XseAjE7hKLVh2YvCFvqfuM,918
-csv_detective/detect_labels/FR/geo/departement/__init__.py,sha256=qnCjAkBGwsKsfLtvW_EgG-9eK_SBgyFrBKE9Q0A7wxI,1199
-csv_detective/detect_labels/FR/geo/insee_canton/__init__.py,sha256=dLJPbSuOQETbl1IBeme5H4KXtDlfPBe5lIfczR4ek48,927
-csv_detective/detect_labels/FR/geo/latitude_l93/__init__.py,sha256=fJrd8pIewZqAkNNfERWD39kK3oxzYy-Paxce66c3UnY,1356
-csv_detective/detect_labels/FR/geo/latitude_wgs_fr_metropole/__init__.py,sha256=xRrXcUUlk7XqHuHbTXUToM3n90_kLXQxdSzMkcc9jIc,1351
-csv_detective/detect_labels/FR/geo/longitude_l93/__init__.py,sha256=1uFQv436tkosABNVU_htAJcggJ6QRlF70-aBgHJHc8A,1109
-csv_detective/detect_labels/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256=dOhUJy_vukt9xFnY2CG4wg1q9vHBUa00mbsu4YSN6xY,1114
-csv_detective/detect_labels/FR/geo/pays/__init__.py,sha256=-k5shWSQnLpDvRWKuGFqt5ScbNyBO__vL-4UrL_hRjQ,1139
-csv_detective/detect_labels/FR/geo/region/__init__.py,sha256=uQKqMZvG4bs0eafvRHV2RwtbwFJ9vCFQNE2Ep23eHq0,1134
+csv_detective/detect_labels/FR/geo/adresse/__init__.py,sha256=fNWFW-Wo3n6azDBfmi0J0qnzP-p2StLxCc9eNiE9NNE,346
+csv_detective/detect_labels/FR/geo/code_commune_insee/__init__.py,sha256=Cr9eyNnP1bLcOx0BlF9ZGZkQDTVuSFjPxvkoZJGs-Eg,379
+csv_detective/detect_labels/FR/geo/code_departement/__init__.py,sha256=Uzufy44ERqIX8wol6tEZg1SrNUcYAWl4AMsWVnL4SLM,355
+csv_detective/detect_labels/FR/geo/code_fantoir/__init__.py,sha256=TUUj3XNlMEK7fl_R5BWBSXYGr_2xzMqIhRTb_GDcnqY,262
+csv_detective/detect_labels/FR/geo/code_postal/__init__.py,sha256=qGGujM5sDqkNZcoVLRRZCh9H9cid9dx2T8jcJsbo3cs,353
+csv_detective/detect_labels/FR/geo/code_region/__init__.py,sha256=gAy0TxV6qL7_SfthSSulouvYJn3C70xMYuqABP61euA,334
+csv_detective/detect_labels/FR/geo/commune/__init__.py,sha256=eTyTtKe1NHTvgaB4jMywIqYRATU2A-E-Tq3m0KDMr6w,261
+csv_detective/detect_labels/FR/geo/departement/__init__.py,sha256=IJy_aKEocrTN39dxK2fE_PoDM4OR9W2rHsR4cULHw9g,512
+csv_detective/detect_labels/FR/geo/insee_canton/__init__.py,sha256=H8iuLwn_x3ctxOL5pi8REqKO5Z3wL4rSDohbSdnnpIM,278
+csv_detective/detect_labels/FR/geo/latitude_l93/__init__.py,sha256=_KjSU6XFeX3Tll5Nb2nnTEhXJXA4-WxqoTov926TGlU,666
+csv_detective/detect_labels/FR/geo/latitude_wgs_fr_metropole/__init__.py,sha256=ME_KjniqDSdAwXP7XnKXyr5IA75KrGSLIhvPNfsux6E,664
+csv_detective/detect_labels/FR/geo/longitude_l93/__init__.py,sha256=jnbtGriHroGKoOmsmCVGJf6sJXzsVkKH21Qf0aamgkk,428
+csv_detective/detect_labels/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256=jnbtGriHroGKoOmsmCVGJf6sJXzsVkKH21Qf0aamgkk,428
+csv_detective/detect_labels/FR/geo/pays/__init__.py,sha256=GW5wEO0g-YXKXerdtyt4VOVg8kKXUsMb7EPf8nKEbH0,452
+csv_detective/detect_labels/FR/geo/region/__init__.py,sha256=P0eVE46w5GAbTgeGnvJgZynQt7EY_Bi_NZ1gmYxP6io,447
 csv_detective/detect_labels/FR/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/other/code_csp_insee/__init__.py,sha256=OIOih96ohL50BXgkopAV6NTXQsp5hP78YC46g_r-hKs,909
-csv_detective/detect_labels/FR/other/code_rna/__init__.py,sha256=Nih32b26tuJs2f_x-XZ-cjD4nobgBhXsMALsQDlz2NM,994
-csv_detective/detect_labels/FR/other/code_waldec/__init__.py,sha256=JcvDvLHlxddehJHEJNAAu3ZmjcJ__6qa4t440CFtKq0,904
-csv_detective/detect_labels/FR/other/csp_insee/__init__.py,sha256=XgcgdjcLA1OdPktRPSPzlXePaK8GYR6SF1DCKSoZ6RA,1013
-csv_detective/detect_labels/FR/other/date_fr/__init__.py,sha256=FoWbiIxDHIcoQmyWMayqmnRedd0I_RuC_0SIhWIXzww,945
-csv_detective/detect_labels/FR/other/insee_ape700/__init__.py,sha256=TnZocEWxNwqcX5Y-c45dW9BCEWUMbwFlqM2p0XRTNWU,1094
-csv_detective/detect_labels/FR/other/sexe/__init__.py,sha256=rn035P9h8PsZ-Fu-v71DxcA_6HH9vmJ8lH-hSPmsflg,926
-csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=utC1MWILaja5dkNfg3T2-0gXgHxOpIi74L2SaS5Z2PE,1073
-csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=zl45o9AtUgAjsH9WZsdU9nDbEXUEOxuRcAX2JOxUe4U,1010
-csv_detective/detect_labels/FR/other/tel_fr/__init__.py,sha256=BeHgQwLDrFABECzDYfuAKmXhAFGqTK9mrjk2w3aecNY,1113
-csv_detective/detect_labels/FR/other/uai/__init__.py,sha256=XYs7d5CipvJcvL1OEIvqKNg1Ubb9nI2x54KG_jW8Sx8,1286
+csv_detective/detect_labels/FR/other/code_csp_insee/__init__.py,sha256=8nl4UCONRg_x5FtdmTGvPnXS8J1ASWCUGr0Ziv32Ngw,221
+csv_detective/detect_labels/FR/other/code_rna/__init__.py,sha256=I7CliSnzWJzAxNlVmbUjMsXThNQe336RzNuBWOXINkc,307
+csv_detective/detect_labels/FR/other/code_waldec/__init__.py,sha256=soWkoyVsSn2E26Sem8Y7u6gyZc7tqzjMJ9VO3aXfLzQ,216
+csv_detective/detect_labels/FR/other/csp_insee/__init__.py,sha256=AI9nqj3zm6_vycAXsXZdsBD7ceNzMzGQL7xZnDZ8nhw,327
+csv_detective/detect_labels/FR/other/date_fr/__init__.py,sha256=4Crk045ZD_tVovI7C-IqjKFz23Ej5-hrFkhZK4OilqA,258
+csv_detective/detect_labels/FR/other/insee_ape700/__init__.py,sha256=N7LzmtNwZERgrwMy3EFHaVBpdiwkt2_9Tt7XVJLff6U,406
+csv_detective/detect_labels/FR/other/sexe/__init__.py,sha256=ZWhc8S9L1X2fFh2g5Ja-LuhsfHg_lALKrur6yDnGDPk,238
+csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=g7Y7IvW9VKO528z1MSPxfFtRB7kQXSiG7QQ-VZRfFEk,386
+csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=-gvdxUnv3LRfje60ljC4F3B2c1LBcWfV3zZbV3VJZ08,323
+csv_detective/detect_labels/FR/other/tel_fr/__init__.py,sha256=pg2nwqw2lphUMUeuuh_8NPi54TPmQFP3c8Dl9yGOxbI,427
+csv_detective/detect_labels/FR/other/uai/__init__.py,sha256=5L6JowK9y6y9uZNg6hWzknMSzh0SurkwQeTINNKTdYY,599
 csv_detective/detect_labels/FR/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py,sha256=Ezpf-7lsk389VKdKMZvZ00rMqq070uSVVb8oko06KGw,1044
-csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py,sha256=5GytrQmPCmr-vndjcAS5cQWOO4RPvrfQh8KqH9qhrCc,904
+csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py,sha256=Vmv7Hp6LxR-bh3aXOBCHYzJVyCHtGoiWzJ40xnfTvdA,357
+csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py,sha256=M4ANAy40vq328DRdB6LudjO9G9duSh7e-RqFr6axXO0,225
 csv_detective/detect_labels/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py,sha256=CUtYIsh08LjNoa-BJkxrYvHuwJBG--u1AK5BN4RDpL4,1035
-csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py,sha256=CUtYIsh08LjNoa-BJkxrYvHuwJBG--u1AK5BN4RDpL4,1035
-csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py,sha256=CUtYIsh08LjNoa-BJkxrYvHuwJBG--u1AK5BN4RDpL4,1035
-csv_detective/detect_labels/geo/json_geojson/__init__.py,sha256=3scv7fZ5cxu5MR8RR-AF4KmGhkZT--CYcFg22IibhkY,1042
-csv_detective/detect_labels/geo/latitude_wgs/__init__.py,sha256=xRrXcUUlk7XqHuHbTXUToM3n90_kLXQxdSzMkcc9jIc,1351
-csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=yL8Fp4DcwOm0f5_5CbSZwbvGD1p3LOkRS7hxz778O7g,1675
-csv_detective/detect_labels/geo/longitude_wgs/__init__.py,sha256=yHhVPefvqgl8Q1fEdstoxDeGyJNkJ-2b1S5cwdF4HTI,1115
+csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py,sha256=biUZP8gAsVpjXLTx1WeS19qR4ia0pzpi6R69wJgu4B0,348
+csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py,sha256=biUZP8gAsVpjXLTx1WeS19qR4ia0pzpi6R69wJgu4B0,348
+csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py,sha256=biUZP8gAsVpjXLTx1WeS19qR4ia0pzpi6R69wJgu4B0,348
+csv_detective/detect_labels/geo/json_geojson/__init__.py,sha256=On8VOCDD0EspZra6fTQCXH4MYao2xmRu-o7xWcab7Jg,355
+csv_detective/detect_labels/geo/latitude_wgs/__init__.py,sha256=ME_KjniqDSdAwXP7XnKXyr5IA75KrGSLIhvPNfsux6E,664
+csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=dbWX1LKpoev7zwWthw9vlwGQp6CSlgYrTBnPpvyNC-A,989
+csv_detective/detect_labels/geo/longitude_wgs/__init__.py,sha256=_8IV2FLtrOjzhQNsk-fsgc9-jbAgzKDVMr4tXu2P-s4,429
 csv_detective/detect_labels/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/other/booleen/__init__.py,sha256=0AvbuPVr7corJLDOu-wNS9BOy6J8XzOPIouS9MyFKHA,957
-csv_detective/detect_labels/other/email/__init__.py,sha256=0VXS8hWILdGRWugx9hEz5yEAnlaoJ6jYX3znkzjlDYE,1118
-csv_detective/detect_labels/other/float/__init__.py,sha256=FD8NlVSZ0TARGKKKCkWYRT9vYwDXpQe7X4V7VPJNUrw,896
-csv_detective/detect_labels/other/int/__init__.py,sha256=I8ff6zX1tsk4JtNWs0V0Vam-BtdiKiGyUkUvIysfbUY,903
-csv_detective/detect_labels/other/money/__init__.py,sha256=kBEGuUy6kYkOI3vC_a7waBciG2ipyV9bhC330U8WaoI,279
-csv_detective/detect_labels/other/money/check_col_name.py,sha256=zgp5eUnf3XRQuxgdEGfxPfUnniO8Pzw19uK0ICr2pf8,414
-csv_detective/detect_labels/other/mongo_object_id/__init__.py,sha256=gyuizUcsQwdwKVmnaGJbauc01SkqhgaXtsq_vWlwsXs,897
-csv_detective/detect_labels/other/twitter/__init__.py,sha256=MGuWhcmZFDcBz16v-g8By_k-RF3UimU7qb8QTAAs8PA,929
-csv_detective/detect_labels/other/url/__init__.py,sha256=NSMvRhtNJgyVr2AQpkI1O-UWdBiovq62WHEmMb3WlOM,1172
-csv_detective/detect_labels/other/uuid/__init__.py,sha256=ePXGCdVfKus67jvdeq5MZA1CA2j47PKjHhWnrsyCAi8,901
+csv_detective/detect_labels/other/booleen/__init__.py,sha256=BZwnfR-Zcv8dqscLrBKhttgwm4Dqq16M0PaGirxYWio,214
+csv_detective/detect_labels/other/email/__init__.py,sha256=Poagn45-eC2a_Wdk5Qs6d2BgYdncCQKZp2yEB50IuNw,431
+csv_detective/detect_labels/other/float/__init__.py,sha256=X0axZN2GAfC_y01zRfIyvOfRsOy2KNQcQ-mlQAKxqT4,216
+csv_detective/detect_labels/other/int/__init__.py,sha256=_1AY7thEBCcgSBQQ2YbY4YaPaxGRQ71BtmaFaX088ig,215
+csv_detective/detect_labels/other/money/__init__.py,sha256=1JRArDZ5r6gtyuKijH_fuuVFVc0f3MN5gPyAf4GPqzs,249
+csv_detective/detect_labels/other/mongo_object_id/__init__.py,sha256=1eoJpaK0mP8Jjh9ljwvG7yG_05fxmAyYoZDdbOVbfw4,209
+csv_detective/detect_labels/other/twitter/__init__.py,sha256=96WhOB6nOutzSFOC5ZJYFSlhHDJRn2SkT4nYNj8E6ww,241
+csv_detective/detect_labels/other/url/__init__.py,sha256=4Ajpdp8W0jS9aHZAAMyUlgefjSgpB7Y6ci29KNkwAoI,485
+csv_detective/detect_labels/other/uuid/__init__.py,sha256=kXVb4oMy-Zv-OYmAIEoNFrBA20l9hbUTdvTfjeMmhjk,213
 csv_detective/detect_labels/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/temp/date/__init__.py,sha256=oI77XxATeJLk27r8Cdg1DmSNYtLl5Se4zay3eG12eJ0,1292
-csv_detective/detect_labels/temp/datetime_iso/__init__.py,sha256=C8ZgzfZWVw6nebMuySpED2HRUho8W4rLxv6qDNpJvas,1127
-csv_detective/detect_labels/temp/datetime_rfc822/__init__.py,sha256=WPSWNPgDPAHBMT-Nv0X-6u3yTQfcsaab2NNiG2-8qgk,1145
-csv_detective/detect_labels/temp/year/__init__.py,sha256=AGkHXXvo_oG9di9p9Glae-c8TIPJ0319isnNKOzBCjk,1120
+csv_detective/detect_labels/temp/date/__init__.py,sha256=w0eeZIseAmPwL4OvCWzZXbxGOIXYRKiZUhEtgHiBXd0,604
+csv_detective/detect_labels/temp/datetime_iso/__init__.py,sha256=d0laZNzHx-kSARs9Re8TZ11GNs99aMz6gXc72CJ6ul4,440
+csv_detective/detect_labels/temp/datetime_rfc822/__init__.py,sha256=53ysj7QgsxXwG1le3zfSJd1oaTTf-Er3jBeYi_A4F9g,458
+csv_detective/detect_labels/temp/year/__init__.py,sha256=7uWaCZY7dOG7nolW46IgBWmcu8K-9jPED-pOlMlErfo,433
 csv_detective/detection/columns.py,sha256=vfE-DKESA6J9Rfsl-a8tjgZfE21VmzArO5TrbzL0KmE,2905
 csv_detective/detection/encoding.py,sha256=tpjJEMNM_2TcLXDzn1lNQPnSRnsWYjs83tQ8jNwTj4E,973
 csv_detective/detection/engine.py,sha256=HiIrU-l9EO5Fbc2Vh8W_Uy5-dpKcQQzlxCqMuWc09LY,1530
@@ -147,20 +146,20 @@ csv_detective/parsing/compression.py,sha256=Fnw5tj-PpBNI8NYsWj5gD-DUoWcVLnsVpiKm
 csv_detective/parsing/csv.py,sha256=11mibDnJhIjykXLGZvA5ZEU5U7KgxIrbyO6BNv6jlro,1626
 csv_detective/parsing/excel.py,sha256=AslE2S1e67o8yTIAIhp-lAnJ6-XqeBBRz1-VMFqhZBM,7055
 csv_detective/parsing/load.py,sha256=u6fbGFZsL2GwPQRzhAXgt32JpUur7vbQdErREHxNJ-w,3661
-csv_detective/parsing/text.py,sha256=rsfk66BCmdpsCOd0kDJ8tmqMsEWd-OeBkEisWc4Ej9k,1246
-csv_detective-0.8.1.dev1362.data/data/share/csv_detective/CHANGELOG.md,sha256=798lqRkhkIMWZgj8UWholpCJ719DOF_bB0hD8y6HM-g,8291
-csv_detective-0.8.1.dev1362.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
-csv_detective-0.8.1.dev1362.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
-csv_detective-0.8.1.dev1362.dist-info/licenses/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
+csv_detective/parsing/text.py,sha256=_TprGi0gHZlRsafizI3dqQhBehZW4BazqxmypMcAZ-o,1824
+csv_detective-0.8.1.dev1416.data/data/share/csv_detective/CHANGELOG.md,sha256=Ar1X9WX1CVoStDzDEOo5O3P0DgRtUUmo70KAYlWLJyQ,8443
+csv_detective-0.8.1.dev1416.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
+csv_detective-0.8.1.dev1416.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
+csv_detective-0.8.1.dev1416.dist-info/licenses/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_example.py,sha256=JeHxSK0IVDcSrOhSZlNGSQv4JAc_r6mzvJM8PfmLTMw,2018
-tests/test_fields.py,sha256=E6kEsp6_W56WW6FXWUl7hggsJv-vsKuOaJ9JLoFmrUw,9964
+tests/test_fields.py,sha256=d2tNvjtal6ZbO646x1GDbp_CGgp-EIcdg2SgMG72J6E,10270
 tests/test_file.py,sha256=9APE1d43lQ8Dk8lwJFNUK_YekYYsQ0ae2_fgpcPE9mk,8116
-tests/test_labels.py,sha256=6MOKrGznkwU5fjZ_3oiB6Scmb480Eu-9geBJs0UDLds,159
+tests/test_labels.py,sha256=Nkr645bUewrj8hjNDKr67FQ6Sy_TID6f3E5Kfkl231M,464
 tests/test_structure.py,sha256=bv-tjgXohvQAxwmxzH0BynFpK2TyPjcxvtIAmIRlZmA,1393
 tests/test_validation.py,sha256=CTGonR6htxcWF9WH8MxumDD8cF45Y-G4hm94SM4lFjU,3246
-csv_detective-0.8.1.dev1362.dist-info/METADATA,sha256=Vk1SkLg14wAGFzxtutlVEFt5q9G__rpclVVR7rvtJOo,1386
-csv_detective-0.8.1.dev1362.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-csv_detective-0.8.1.dev1362.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.8.1.dev1362.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
-csv_detective-0.8.1.dev1362.dist-info/RECORD,,
+csv_detective-0.8.1.dev1416.dist-info/METADATA,sha256=aCmQVKUNFvJLzTS8DHELQme0GS9jwrHGod4JLWIGt1o,1386
+csv_detective-0.8.1.dev1416.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+csv_detective-0.8.1.dev1416.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
+csv_detective-0.8.1.dev1416.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
+csv_detective-0.8.1.dev1416.dist-info/RECORD,,

{csv_detective-0.8.1.dev1362.dist-info → csv_detective-0.8.1.dev1416.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.7.1)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tests/test_fields.py

@@ -293,8 +293,17 @@ fields = {
         False: ["adresse@mail"],
     },
     url: {
-        True: ["www.etalab.data.gouv.fr"],
-        False: ["une phrase avec un @ dedans"],
+        True: [
+            "www.data.gouv.fr",
+            "http://data.gouv.fr",
+            "https://www.youtube.com/@data-gouv-fr",
+            (
+                "https://tabular-api.data.gouv.fr/api/resources/"
+                "aaaaaaaa-1111-bbbb-2222-cccccccccccc/data/"
+                "?score__greater=0.9&decompte__exact=13"
+            ),
+        ],
+        False: ["tmp@data.gouv.fr"],
     },
     uuid: {
         True: ["884762be-51f3-44c3-b811-1e14c5d89262"],

tests/test_labels.py

@@ -1,7 +1,23 @@
-from csv_detective.detect_labels.other import money
+import pytest
+
+from csv_detective.detect_labels import latitude_wgs, money
 
 
 # money labels
 def test_money_labels():
     header = "Montant total"
-    assert money._is(header) == 1.0
+    assert money._is(header) == 0.5
+
+
+@pytest.mark.parametrize(
+    "params", [
+        ("latitude", 1.0),
+        ("lat", 1.0),
+        ("coord_lat", 0.5),
+        ("y", 1.0),
+        ("nb_cycles", 0.0),
+    ]
+)
+def test_latitude(params):
+    header, expected = params
+    assert expected == latitude_wgs._is(header)

csv_detective/detect_labels/other/money/check_col_name.py

@@ -1,8 +0,0 @@
-def is_col_name_related_to_money(name):
-    # TODO : make this a little bit more clever (spacy ?)
-    col_name_related_to_money = False
-    money_themes = ['budget', 'salaire', 'euro', 'euros', 'prêt', 'montant']
-    # TODO attention 'européeen' est détecté OK
-    for theme in money_themes:
-        col_name_related_to_money = col_name_related_to_money or (theme in name)
-    return col_name_related_to_money